Analysis of the algorithm: From rankings to backup genes.

Ranking section

For each of the affected genes present in the list, a ranking with the score and percentile of every possible gene was obtained. Once this was done, the position for every known backup gene was obtained and the statistical descriptor of all the values calculated.

Table 1. Backup position values for every kernel and net before integration.

Net Kernel Elements Min Max Average Standard_Deviation
cellular_component el 27 0.007 0.957 0.522 0.287
cellular_component ka 27 0.0 0.884 0.197 0.245
cellular_component rf 27 0.0 0.883 0.194 0.245
disease ct 16 0.001 0.692 0.09 0.201
disease el 16 0.005 0.562 0.081 0.133
disease ka 16 0.0 0.721 0.099 0.229
disease rf 16 0.001 0.694 0.09 0.201
molecular_function el 27 0.088 0.973 0.469 0.276
molecular_function ka 27 0.0 0.97 0.271 0.319
molecular_function rf 27 0.0 0.994 0.272 0.321
phenotype ct 17 0.0 0.876 0.161 0.246
phenotype el 17 0.052 0.855 0.473 0.223
phenotype ka 17 0.0 0.955 0.165 0.258
phenotype rf 17 0.0 0.883 0.161 0.247

Table 2. Backup position values for every kernel after integration

Integration Kernel Elements Min Max Average Standard_Deviation
integration_mean_by_presence ct 27 0.01 0.921 0.561 0.244
integration_mean_by_presence el 27 0.024 0.96 0.404 0.195
integration_mean_by_presence ka 27 0.024 0.85 0.433 0.209
integration_mean_by_presence rf 27 0.023 0.986 0.478 0.24
mean ct 27 0.012 0.923 0.531 0.242
mean el 27 0.024 0.96 0.434 0.221
mean ka 27 0.026 0.974 0.472 0.247
mean rf 27 0.023 0.986 0.464 0.254

CDF plots of non integrated kernels

CDF plots of non integrated kernels